Contrastive Language-Image Pre-training (CLIP) learns robust visual models through language supervision, making it a crucial visual encoding technique for various applications. However, CLIP struggles with comprehending spatial concepts in images, potentially restricting the spatial intelligence of CLIP-based AI systems. In this work, we propose SpatialCLIP, an enhanced version of CLIP with better spatial understanding capabilities. To capture the intricate 3D spatial relationships in images, we improve both "visual model" and "language supervision" of CLIP. Specifically, we design 3D-inspired ViT to replace the standard ViT in CLIP. By lifting 2D image tokens into 3D space and incorporating design insights from point cloud networks, our visual model gains greater potential for spatial perception. Meanwhile, captions with accurate and detailed spatial information are very rare. To explore better language supervision for spatial understanding, we re-caption images and perturb their spatial phrases as negative descriptions, which compels the visual model to seek spatial cues to distinguish these hard negative captions. With the enhanced visual model, we introduce SpatialLLaVA, following the same LLaVA-1.5 training protocol, to investigate the importance of visual representations for MLLM’s spatial intelligence. Furthermore, we create SpatialBench, a benchmark specifically designed to evaluate CLIP and MLLM in spatial reasoning. Spatial-CLIP and SpatialLLaVA achieve substantial performance improvements, demonstrating stronger capabilities in spatial perception and reasoning, while maintaining comparable results on general-purpose benchmarks.

Semi-supervised semantic segmentation (SSS) aims at learning rich visual knowledge from cheap unlabeled images to enhance semantic segmentation capability. Among recent works, UniMatch (Yang et al. 2023) improves its precedents tremendously by amplifying the practice of weak-to-strong consistency regularization. Subsequent works typically follow similar pipelines and propose various delicate designs. Despite the achieved progress, strangely, even in this flourishing era of numerous powerful vision models, almost all SSS works are still sticking to 1) using outdated ResNet encoders with small-scale ImageNet-1 K pre-training, and 2) evaluation on simple Pascal and Cityscapes datasets. In this work, we argue that, it is necessary to switch the baseline of SSS from ResNet-based encoders to more capable ViT-based encoders (e.g., DINOv2) that are pre-trained on massive data. A simple update on the encoder (even using 2× fewer parameters) can bring more significant improvement than careful method designs. Built on this competitive baseline, we present our upgraded and simplified UniMatch V2, inheriting the core spirit of weak-to-strong consistency from V1, but requiring less training cost and providing consistently better results. Additionally, witnessing the gradually saturated performance on Pascal and Cityscapes, we appeal that we should focus on more challenging benchmarks with complex taxonomy, such as ADE20K and COCO datasets.

This work presents Depth Anything11While the grammatical soundness of this name may be questionable, we treat it as a whole and pay homage to Segment Anything [26]., a highly practical solution for robust monocular depth estimation. Without pursuing novel technical modules, we aim to build a simple yet powerful foundation model dealing with any images under any circumstances. To this end, we scale up the dataset by designing a data engine to collect and automatically annotate large-scale unlabeled data (~62M), which significantly enlarges the data coverage and thus is able to reduce the generalization error. We investigate two simple yet effective strategies that make data scaling-up promising. First, a more challenging optimization target is created by leveraging data augmentation tools. It compels the model to actively seek extra visual knowledge and acquire robust representations. Second, an auxiliary supervision is developed to enforce the model to inherit rich semantic priors from pre-trained encoders. We evaluate its zero-shot capabilities extensively, including six public datasets and randomly captured photos. It demonstrates impressive generalization ability (Figure 1). Further, through fine-tuning it with metric depth information from NYUv2 and KITTI, new SOTAs are set. Our better depth model also results in a better depth-conditioned ControlNet. Our models are released here.

This work presents Depth Anything V2. Without pursuing fancy techniques, we aim to reveal crucial findings to pave the way towards building a powerful monocular depth estimation model. Notably, compared with V1, this version produces much finer and more robust depth predictions through three key practices: 1) replacing all labeled real images with synthetic images, 2) scaling up the capacity of our teacher model, and 3) teaching student models via the bridge of large-scale pseudo-labeled real images. Compared with the latest models built on Stable Diffusion, our models are significantly more efficient (more than 10x faster) and more accurate. We offer models of different scales (ranging from 25M to 1.3B params) to support extensive scenarios. Benefiting from their strong generalization capability, we fine-tune them with metric depth labels to obtain our metric depth models. In addition to our models, considering the limited diversity and frequent noise in current test sets, we construct a versatile evaluation benchmark with sparse depth annotations to facilitate future research. Models are available at https://github.com/DepthAnything/Depth-Anything-V2.

High resolution range profile (HRRP) provides abundant target information but is susceptible to external electromagnetic interference. While infrared sensor possesses strong anti-jamming capability, it has limited detection range and is vulnerable to weather conditions, leading to reduced imaging resolution. The integration of radar and infrared sensors can synergize their respective strengths to not only improve the reliability and robustness of the system but also enhance the credibility and accuracy of the data. However, there exist many challenges in the research on the fusion of heterogeneous data like HRRP 1D data and infrared 2D data. In this letter, a radar infrared sensor fusion method based on hierarchical features mining (HFM) is proposed to solve the problems above. The method is applied to multi-target recognition tasks to verify the effectiveness. The results demonstrate that the proposed method can enhance the information completeness of the target and improve the accuracy of target recognition.

In this work, we revisit the weak-to-strong consistency framework, popularized by FixMatch from semi-supervised classification, where the prediction of a weakly perturbed image serves as supervision for its strongly perturbed version. Intriguingly, we observe that such a simple pipeline already achieves competitive results against recent advanced works, when transferred to our segmentation scenario. Its success heavily relies on the manual design of strong data augmentations, however, which may be limited and inadequate to explore a broader perturbation space. Motivated by this, we propose an auxiliary feature perturbation stream as a supplement, leading to an expanded perturbation space. On the other, to sufficiently probe original image-level augmentations, we present a dual-stream perturbation technique, enabling two strong views to be simultaneously guided by a common weak view. Consequently, our overall Unified Dual-Stream Perturbations approach (UniMatch) surpasses all existing methods significantly across all evaluation protocols on the Pascal, Cityscapes, and COCO benchmarks. Its superiority is also demonstrated in remote sensing interpretation and medical image analysis. We hope our reproduced FixMatch and our results can inspire more future works.

Recent studies on semi-supervised semantic segmentation (SSS) have seen fast progress. Despite their promising performance, current state-of-the-art methods tend to increasingly complex designs at the cost of introducing more network components and additional training procedures. Differently, in this work, we follow a standard teacher-student framework and propose AugSeg, a simple and clean approach that focuses mainly on data perturbations to boost the SSS performance. We argue that various data augmentations should be adjusted to better adapt to the semi-supervised scenarios instead of directly applying these techniques from supervised learning. Specifically, we adopt a simplified intensity-based augmentation that selects a random number of data transformations with uniformly sampling distortion strengths from a continuous space. Based on the estimated confidence of the model on different unlabeled samples, we also randomly inject labelled information to augment the unlabeled samples in an adaptive manner. Without bells and whistles, our simple AugSeg can readily achieve new state-of-the-art performance on SSS benchmarks under different partition protocols11Code and logs: https://github.com/zhenzhao/AugSeg..

Deep co-training has been introduced to semi-supervised segmentation and achieves impressive results, yet few studies have explored the working mechanism behind it. In this work, we revisit the core assumption that supports co-training: multiple compatible and conditionally independent views. By theoretically deriving the generalization upper bound, we prove the prediction similarity between two models negatively impacts the model’s generalization ability. However, most current co-training models are tightly coupled together and violate this assumption. Such coupling leads to the homogenization of networks and confirmation bias which consequently limits the performance. To this end, we explore different dimensions of co-training and systematically increase the diversity from the aspects of input domains, different augmentations and model architectures to counteract homogenization. Our Diverse Co-training outperforms the state-of-the-art (SOTA) methods by a large margin across different evaluation protocols on the Pascal and Cityscapes. For example, we achieve the best mIoU of 76.2%, 77.7% and 80.2% on Pascal with only 92, 183 and 366 labeled images, surpassing the previous best results by more than 5%.

Semi-supervised learning is attracting blooming attention, due to its success in combining unlabeled data. To mitigate potentially incorrect pseudo labels, recent frameworks mostly set a fixed confidence threshold to discard uncertain samples. This practice ensures high-quality pseudo labels, but incurs a relatively low utilization of the whole unlabeled set. In this work, our key insight is that these uncertain samples can be turned into certain ones, as long as the confusion classes for the top-1 class are detected and removed. Invoked by this, we propose a novel method dubbed ShrinkMatch to learn uncertain samples. For each uncertain sample, it adaptively seeks a shrunk class space, which merely contains the original top-1 class, as well as remaining less likely classes. Since the confusion ones are removed in this space, the re-calculated top-1 confidence can satisfy the pre-defined threshold. We then impose a consistency regularization between a pair of strongly and weakly augmented samples in the shrunk space to strive for discriminative representations. Furthermore, considering the varied reliability among uncertain samples and the gradually improved model during training, we correspondingly design two reweighting principles for our uncertain loss. Our method exhibits impressive performance on widely adopted benchmarks.

Semantic segmentation has witnessed tremendous progress due to the proposal of various advanced network architectures. However, they are extremely hungry for delicate annotations to train, and the acquisition is laborious and unaffordable. Therefore, we present FreeMask in this work, which resorts to synthetic images from generative models to ease the burden of both data collection and annotation procedures. Concretely, we first synthesize abundant training images conditioned on the semantic masks provided by realistic datasets. This yields extra well-aligned image-mask training pairs for semantic segmentation models. We surprisingly observe that, solely trained with synthetic images, we already achieve comparable performance with real ones (e.g., 48.3 vs. 48.5 mIoU on ADE20K, and 49.3 vs. 50.5 on COCO-Stuff). Then, we investigate the role of synthetic images by joint training with real images, or pre-training for real images. Meantime, we design a robust filtering principle to suppress incorrectly synthesized regions. In addition, we propose to inequally treat different semantic masks to prioritize those harder ones and sample more corresponding synthetic images for them. As a result, either jointly trained or pre-trained with our filtered and re-sampled synthesized images, segmentation models can be greatly enhanced, e.g., from 48.7 to 52.0 on ADE20K.

Self-training via pseudo labeling is a conventional, simple, and popular pipeline to leverage unlabeled data. In this work, we first construct a strong baseline of self-training (namely ST) for semi-supervised semantic segmentation via injecting strong data augmentations (SDA) on unlabeled images to alleviate overfitting noisy labels as well as decouple similar predictions between the teacher and student. With this simple mechanism, our ST outperforms all existing methods without any bells and whistles, e.g., iterative retraining. Inspired by the impressive results, we thoroughly investigate the SDA and provide some empirical analysis. Nevertheless, incorrect pseudo labels are still prone to accumulate and degrade the performance. To this end, we further propose an advanced self-training framework (namely ST++), that performs selective re-training via prioritizing reliable unlabeled images based on holistic prediction-level stability. Concretely, several model checkpoints are saved in the first stage supervised training, and the discrepancy of their predictions on the unlabeled image serves as a measurement for reliability. Our image-level selection offers holistic contextual information for learning. We demonstrate that it is more suitable for segmentation than common pixel-wise selection. As a result, ST+ further boosts the performance of our ST. Code is available at https://github.com/LiheYoung/ST-PlusPlus.

Few-shot segmentation (FSS) aims to segment unseen classes given only a few annotated samples. Existing methods suffer the problem of feature undermining, i.e., potential novel classes are treated as background during training phase. Our method aims to alleviate this problem and enhance the feature embedding on latent novel classes. In our work, we propose a novel joint-training framework. Based on conventional episodic training on support-query pairs, we introduce an additional mining branch that exploits latent novel classes via transferable sub-clusters, and a new rectification technique on both background and fore-ground categories to enforce more stable prototypes. Over and above that, our transferable sub-cluster has the ability to leverage extra unlabeled data for further feature enhancement. Extensive experiments on two FSS benchmarks demonstrate that our method outperforms previous state-of-the-art by a large margin of 3.7% mIOU on PASCAL-5iand 7.0% mIOU on COCO-20iat the cost of 74% fewer parameters and 2.5x faster inference speed. The source code is available at https://github.com/LiheYoung/MiningFSS.