Starting from the seminal work of Fully Convolutional Networks (FCN), there has been significant progress on semantic segmentation. However, deep learning models often require large amounts of pixelwise annotations to train accurate and robust models. Given the prohibitively expensive annotation cost of segmentation masks, we introduce a self-training framework in this paper to leverage pseudo labels generated from unlabeled data. In order to handle the data imbalance problem of semantic segmentation, we propose a centroid sampling strategy to uniformly select training samples from every class within each epoch. We also introduce a fast training schedule to alleviate the computational burden. This enables us to explore the usage of large amounts of pseudo labels. Our Centroid Sampling based Self-Training framework (CSST) achieves state-of-the-art results on Cityscapes and CamVid datasets. On PASCAL VOC 2012 test set, our models trained with the original train set even outperform the same models trained on the much bigger augmented train set. This indicates the effectiveness of CSST when there are fewer annotations. We also demonstrate promising few-shot generalization capability from Cityscapes to BDD100K and from Cityscapes to Mapillary datasets.

Vision Transformer (ViT) has demonstrated promising performance in various computer vision tasks, and recently attracted a lot of research attention. Many recent works have focused on proposing new architectures to improve ViT and deploying it into real-world applications. However, little effort has been made to analyze and understand ViT’s architecture design space and its implication for hardware costs on different devices. In this work, by simply scaling ViT’s depth, width, input size, and other basic configurations, we show that a scaled vanilla ViT model without bells and whistles can achieve comparable or superior accuracy-efficiency trade-off than most of the latest ViT variants. Specifically, compared with DeiT-Tiny, our scaled model achieves a ↑ 1.9% higher ImageNet top-1 accuracy under the same FLOPs and a ↑ 3.7% better ImageNet top-1 accuracy under the same latency on an NVIDIA Edge GPU TX2. Motivated by this, we further investigate the extracted scaling strategies from the following two aspects: (1) can these scaling strategies be transferred across different real hardware devices ? and (2) can these scaling strategies be transferred to different ViT variants and tasks ?. For (1), our exploration, based on various devices with different resource budgets, indicates that the transferability effectiveness depends on the underlying device together with its corresponding deployment tool. For (2), we validate the effective transferability of the aforementioned scaling strategies obtained from a vanilla ViT model on top of an image classification task to the PiT model, a strong ViT variant targeting efficiency as well as object detection and video classification tasks. In particular, when transferred to PiT, our scaling strategies lead to a boosted ImageNet top-1 accuracy of from 74.6% to 76.7% (↑ 2.1%) under the same 0.7G FLOPs. When transferred to the COCO object detection task, the average precision is boosted by ↑ 0.7% under a similar throughput on a V100 GPU.

Open-vocabulary semantic segmentation aims to segment an image into semantic regions according to text descriptions, which may not have been seen during training. Recent two-stage methods first generate class-agnostic mask proposals and then leverage pre-trained vision-language models, e.g., CLIP, to classify masked regions. We identify the performance bottleneck of this paradigm to be the pre-trained CLIP model, since it does not perform well on masked images. To address this, we propose to finetune CLIP on a collection of masked image regions and their corresponding text descriptions. We collect training data by mining an existing image-caption dataset (e.g., COCO Captions), using CLIP to match masked image regions to nouns in the image captions. Compared with the more precise and manually annotated segmentation labels with fixed classes (e.g., COCO-Stuff), we find our noisy but diverse dataset can better retain CLIP's generalization ability. Along with finetuning the entire model, we utilize the “blank” areas in masked images using a method we dub mask prompt tuning. Experiments demonstrate mask prompt tuning brings significant improvement without modifying any weights of CLIP, and it can further improve a fully finetuned model. In particular, when trained on COCO and evaluated on ADE20K-150, our best model achieves 29.6% mIoU, which is +8.5% higher than the previous state-of-the-art. For the first time, open-vocabulary generalist models match the performance of supervised specialist models in 2017 without dataset specific adaptations.

Computational surface modeling that underlies material recognition has transitioned from reflectance modeling using in-lab controlled radiometric measurements to image-based representations based on internet-mined single-view images captured in the scene. We take a middle-ground approach for material recognition that takes advantage of both rich radiometric cues and flexible image capture. A key concept is differential angular imaging, where small angular variations in image capture enables angular-gradient features for an enhanced appearance representation that improves recognition. We build a large-scale material database, Ground Terrain in Outdoor Scenes (GTOS) database, to support ground terrain recognition for applications such as autonomous driving and robot navigation. The database consists of over 30,000 images covering 40 classes of outdoor ground terrain under varying weather and lighting conditions. We develop a novel approach for material recognition called texture-encoded angular network (TEAN) that combines deep encoding pooling of RGB information and differential angular images for angular-gradient features to fully leverage this large dataset. With this novel network architecture, we extract characteristics of materials encoded in the angular and spatial gradients of their appearance. Our results show that TEAN achieves recognition performance that surpasses single view performance and standard (non-differential/large-angle sampling) multiview performance.

We present GluonCV and GluonNLP, the deep learning toolkits for computer vision and natural language processing based on Apache MXNet (incubating). These toolkits provide state-of-the-art pre-trained models, training scripts, and training logs, to facilitate rapid prototyping and promote reproducible research. We also provide modular APIs with flexible building blocks to enable efficient customization. Leveraging the MXNet ecosystem, the deep learning models in GluonCV and GluonNLP can be deployed onto a variety of platforms with different programming languages. The Apache 2.0 license has been adopted by GluonCV and GluonNLP to allow for software distribution, modification, and usage.

Recent work has achieved great success in utilizing global contextual information for semantic segmentation, including increasing the receptive field and aggregating pyramid feature representations. In this paper, we go beyond global context and explore the fine-grained representation using co-occurrent features by introducing Co-occurrent Feature Model, which predicts the distribution of co-occurrent features for a given target. To leverage the semantic context in the co-occurrent features, we build an Aggregated Co-occurrent Feature (ACF) Module by aggregating the probability of the co-occurrent feature with the co-occurrent context. ACF Module learns a fine-grained spatial invariant representation to capture co-occurrent context information across the scene. Our approach significantly improves the segmentation results using FCN and achieves superior performance 54.0% mIoU on Pascal Context, 87.2% mIoU on Pascal VOC 2012 and 44.89% mIoU on ADE20K datasets. The source code and complete system will be publicly available upon publication.

Much of the recent progress made in image classification research can be credited to training procedure refinements, such as changes in data augmentations and optimization methods. In the literature, however, most refinements are either briefly mentioned as implementation details or only visible in source code. In this paper, we will examine a collection of such refinements and empirically evaluate their impact on the final model accuracy through ablation study. We will show that, by combining these refinements together, we are able to improve various CNN models significantly. For example, we raise ResNet-50's top-1 validation accuracy from 75.3% to 79.29% on ImageNet. We will also demonstrate that improvement on image classification accuracy leads to better transfer learning performance in other application domains such as object detection and semantic segmentation.

Style transfer methods have achieved significant success in recent years with the use of convolutional neural networks. However, many of these methods concentrate on artistic style transfer with few constraints on the output image appearance. We address the challenging problem of transferring face texture from a style face image to a content face image in a photorealistic manner without changing the identity of the original content image. Our framework for face texture transfer (FaceTex) augments the prior work of MRF-CNN with a novel facial semantic regularization that incorporates a face prior regularization smoothly suppressing the changes around facial meso-structures (e.g eyes, nose and mouth) and a facial structure loss function which implicitly preserves the facial structure so that face texture can be transferred without changing the original identity. We demonstrate results on face images and compare our approach with recent state-of-the-art methods. Our results demonstrate superior texture transfer because of the ability to maintain the identity of the original face image.

Recent work has made significant progress in improving spatial resolution for pixelwise labeling with Fully Convolutional Network (FCN) framework by employing Dilated/Atrous convolution, utilizing multi-scale features and refining boundaries. In this paper, we explore the impact of global contextual information in semantic segmentation by introducing the Context Encoding Module, which captures the semantic context of scenes and selectively highlights class-dependent featuremaps. The proposed Context Encoding Module significantly improves semantic segmentation results with only marginal extra computation cost over FCN. Our approach has achieved new state-of-the-art results 51.7% mIoU on PASCAL-Context, 85.9% mIoU on PASCAL VOC 2012. Our single model achieves a final score of 0.5567 on ADE20K test set, which surpasses the winning entry of COCO-Place Challenge 2017. In addition, we also explore how the Context Encoding Module can improve the feature representation of relatively shallow networks for the image classification on CIFAR-10 dataset. Our 14 layer network has achieved an error rate of 3.45%, which is comparable with state-of-the-art approaches with over 10Ã- more layers. The source code for the complete system are publicly available1.

We present a texture network called Deep Encoding Pooling Network (DEP) for the task of ground terrain recognition. Recognition of ground terrain is an important task in establishing robot or vehicular control parameters, as well as for localization within an outdoor environment. The architecture of DEP integrates orderless texture details and local spatial information and the performance of DEP surpasses state-of-the-art methods for this task. The GTOS database (comprised of over 30,000 images of 40 classes of ground terrain in outdoor scenes) enables supervised recognition. For evaluation under realistic conditions, we use test images that are not from the existing GTOS dataset, but are instead from hand-held mobile phone videos of similar terrain. This new evaluation dataset, GTOS-mobile, consists of 81 videos of 31 classes of ground terrain such as grass, gravel, asphalt and sand. The resultant network shows excellent performance not only for GTOS-mobile, but also for more general databases (MINC and DTD). Leveraging the discriminant features learned from this network, we build a new texture manifold called DEP-manifold. We learn a parametric distribution in feature space in a fully supervised manner, which gives the distance relationship among classes and provides a means to implicitly represent ambiguous class boundaries. The source code and database are publicly available1.

Material recognition for real-world outdoor surfaces has become increasingly important for computer vision to support its operation in the wild. Computational surface modeling that underlies material recognition has transitioned from reflectance modeling using in-lab controlled radiometric measurements to image-based representations based on internet-mined images of materials captured in the scene. We propose to take a middle-ground approach for material recognition that takes advantage of both rich radiometric cues and flexible image capture. We realize this by developing a framework for differential angular imaging, where small angular variations in image capture provide an enhanced appearance representation and significant recognition improvement. We build a large-scale material database, Ground Terrain in Outdoor Scenes (GTOS) database, geared towards real use for autonomous agents. The database consists of over 30,000 images covering 40 classes of outdoor ground terrain under varying weather and lighting conditions. We develop a novel approach for material recognition called a Differential Angular Imaging Network (DAIN) to fully leverage this large dataset. With this novel network architecture, we extract characteristics of materials encoded in the angular and spatial gradients of their appearance. Our results show that DAIN achieves recognition performance that surpasses single view or coarsely quantized multiview images. These results demonstrate the effectiveness of differential angular imaging as a means for flexible, in-place material recognition.

We propose a Deep Texture Encoding Network (Deep-TEN) with a novel Encoding Layer integrated on top of convolutional layers, which ports the entire dictionary learning and encoding pipeline into a single model. Current methods build from distinct components, using standard encoders with separate off-the-shelf features such as SIFT descriptors or pre-trained CNN features for material recognition. Our new approach provides an end-to-end learning framework, where the inherent visual vocabularies are learned directly from the loss function. The features, dictionaries, encoding representation and the classifier are all learned simultaneously. The representation is orderless and therefore is particularly useful for material and texture recognition. The Encoding Layer generalizes robust residual encoders such as VLAD and Fisher Vectors, and has the property of discarding domain specific information which makes the learned convolutional features easier to transfer. Additionally, joint training using multiple datasets of varied sizes and class labels is supported resulting in increased recognition performance. The experimental results show superior performance as compared to state-of-the-art methods using gold-standard databases such as MINC-2500, Flickr Material Database, KTH-TIPS-2b, and two recent databases 4D-Light-Field-Material and GTOS. The source code for the complete system are publicly available1.

We introduce a novel method for using reflectance to identify materials. Reflectance offers a unique signature of the material but is challenging to measure and use for recognizing materials due to its high-dimensionality. In this work, one-shot reflectance of a material surface which we refer to as a reflectance disk is capturing using a unique optical camera. The pixel coordinates of these reflectance disks correspond to the surface viewing angles. The reflectance has class-specific stucture and angular gradients computed in this reflectance space reveal the material class. These reflectance disks encode discriminative information for efficient and accurate material recognition. We introduce a framework called reflectance hashing that models the reflectance disks with dictionary learning and binary hashing. We demonstrate the effectiveness of reflectance hashing for material recognition with a number of real-world materials.