Recently, self-supervised large-scale visual pre-training models have shown great promise in representing pixel-level semantic relationships, significantly promoting the development of unsupervised dense prediction tasks, e.g., unsupervised semantic segmentation (USS). The extracted relationship among pixel-level representations typically contains rich class-aware information that semantically identical pixel embeddings in the representation space gather together to form sophisticated concepts. However, leveraging the learned models to ascertain semantically consistent pixel groups or regions in the image is non-trivial since over/ under-clustering overwhelms the conceptualization procedure under various semantic distributions of different images. In this work, we investigate the pixel-level semantic aggregation in self-supervised ViT pre-trained models as image Segmentation and propose the Adaptive Conceptualization approach for USS, termed ACSeg. Concretely, we explicitly encode concepts into learnable prototypes and design the Adaptive Concept Generator (ACG), which adaptively maps these prototypes to informative concepts for each image. Meanwhile, considering the scene complexity of different images, we propose the modularity loss to optimize ACG independent of the concept number based on estimating the intensity of pixel pairs belonging to the same concept. Finally, we turn the USS task into classifying the discovered concepts in an unsupervised manner. Extensive experiments with state-of-the-art results demonstrate the effectiveness of the proposed ACSeg.

Semi-supervised learning (SSL) essentially pursues class boundary exploration with less dependence on human annotations. Although typical attempts focus on ameliorating the inevitable error-prone pseudo-labeling, we think differently and resort to exhausting informative semantics from multiple probably correct candidate labels. In this paper, we introduce Fuzzy Positive Learning (FPL) for accurate SSL semantic segmentation in a plug-and-play fashion, targeting adaptively encouraging fuzzy positive predictions and suppressing highly-probable negatives. Being conceptually simple yet practically effective, FPL can remarkably alleviate interference from wrong pseudo labels and progressively achieve clear pixel-level semantic discrimination. Concretely, our FPL approach consists of two main components, including fuzzy positive assignment (FPA) to provide an adaptive number of labels for each pixel and fuzzy positive regularization (FPR) to restrict the predictions of fuzzy positive categories to be larger than the rest under different perturbations. Theoretical analysis and extensive experiments on Cityscapes and VOC 2012 with consistent performance gain justify the superiority of our approach. Codes are provided in https://github.com/qpc1611094/FPL.

Interactive segmentation enables users to segment as needed by providing cues of objects, which introduces human-computer interaction for many fields, such as image editing and medical image analysis. Typically, massive and expansive pixel-level annotations are spent to train deep models by object-oriented interactions with manually labeled object masks. In this work, we reveal that informative interactions can be made by simulation with semantic-consistent yet diverse region exploration in an unsupervised paradigm. Concretely, we introduce a Multi-granularity Interaction Simulation (MIS) approach to open up a promising direction for unsupervised interactive segmentation. Drawing on the high-quality dense features produced by recent self-supervised models, we propose to gradually merge patches or regions with similar features to form more extensive regions and thus, every merged region serves as a semantic-meaningful multi-granularity proposal. By randomly sampling these proposals and simulating possible interactions based on them, we provide meaningful interaction at multiple granularities to teach the model to understand interactions. Our MIS significantly outperforms non-deep learning unsupervised methods and is even comparable with some previous deep-supervised methods without any annotation.

Position information is critical for Vision Transformers (VTs) due to the permutation-invariance of self-attention operations. A typical way to introduce position information is adding the absolute Position Embedding (PE) to patch embedding before entering VTs. However, this approach operates the same Layer Normalization (LN) to token embedding and PE, and delivers the same PE to each layer. This results in restricted and monotonic PE across layers, as the shared LN affine parameters are not dedicated to PE, and the PE cannot be adjusted on a per-layer basis. To overcome these limitations, we propose using two independent LNs for token embeddings and PE in each layer, and progressively delivering PE across layers. By implementing this approach, VTs will receive layer-adaptive and hierarchical PE. We name our method as Layer-adaptive Position Embedding, abbreviated as LaPE, which is simple, effective, and robust. Extensive experiments on image classification, object detection, and semantic segmentation demonstrate that LaPE significantly outperforms the default PE method. For example, LaPE improves +1.06% for CCT on CIFAR100, +1.57% for DeiT-Ti on ImageNet-1K, +0.7 box AP and +0.5 mask AP for ViT-Adapter-Ti on COCO, and +1.37 mIoU for tiny Segmenter on ADE20K. This is remarkable considering LaPE only increases negligible parameters, memory, and computational cost.

Text-video retrieval is a challenging cross-modal task, which aims to align visual entities with natural language descriptions. Current methods either fail to leverage the local details or are computationally expensive. What's worse, they fail to leverage the heterogeneous concepts in data. In this paper, we propose the Disentangled Conceptualization and Set-to-set Alignment (DiCoSA) to simulate the conceptualizing and reasoning process of human beings. For disentangled conceptualization, we divide the coarse feature into multiple latent factors related to semantic concepts. For set-to-set alignment, where a set of visual concepts correspond to a set of textual concepts, we propose an adaptive pooling method to aggregate semantic concepts to address the partial matching. In particular, since we encode concepts independently in only a few dimensions, DiCoSA is superior at efficiency and granularity, ensuring fine-grained interactions using a similar computational complexity as coarse-grained alignment. Extensive experiments on five datasets, including MSR-VTT, LSMDC, MSVD, ActivityNet, and DiDeMo, demonstrate that our method outperforms the existing state-of-the-art methods.

Video question answering aims at answering a question about the video content by reasoning the alignment semantics within them. However, since relying heavily on human instructions, i.e., annotations or priors, current contrastive learning-based VideoQA methods remains challenging to perform fine-grained visual-linguistic alignments. In this work, we innovatively resort to game theory, which can simulate complicated relationships among multiple players with specific interaction strategies, e.g., video, question, and answer as ternary players, to achieve fine-grained alignment for VideoQA task. Specifically, we carefully design a VideoQA-specific interaction strategy to tailor the characteristics of VideoQA, which can mathematically generate the fine-grained visual-linguistic alignment label without label-intensive efforts. Our TG-VQA outperforms existing state-of-the-art by a large margin (more than 5%) on long-term and short-term VideoQA datasets, verifying its effectiveness and generalization ability. Thanks to the guidance of game-theoretic interaction, our model impressively convergences well on limited data (10^4 videos), surpassing most of those pre-trained on large-scale data (10^7 videos).

The strong correlation between neurons or filters can significantly weaken the generalization ability of neural networks. Inspired by the well-known Tammes problem, we propose a novel diversity regularization method to address this issue, which makes the normalized weight vectors of neurons or filters distributed on a hypersphere as uniformly as possible, through maximizing the minimal pairwise angles (MMA). This method can easily exert its effect by plugging the MMA regularization term into the loss function with negligible computational overhead. The MMA regularization is simple, efficient, and effective. Therefore, it can be used as a basic regularization method in neural network training. Extensive experiments demonstrate that MMA regularization is able to enhance the generalization ability of various modern models and achieves considerable performance improvements on CIFAR100 and TinyImageNet datasets. In addition, experiments on face verification show that MMA regularization is also effective for feature learning. Code is available at: https://github.com/wznpub/MMA_Regularization.

Most of the discriminative feature learning methods are specifically developed for metric learning, however, the effectiveness may be not obvious for other tasks. In this letter, we propose a novel discrimination regularization method for image classification, which enhances the intra-class compactness and inter-class discrepancy simultaneously, through decreasing the minimalangle (DMA) between the feature vector and any one of the weight vectors in classification layer. This method can robustly improve the discriminability and generalizability of neural networks and easily exert its effect by plugging the DMA regularization term into the loss function with negligible computational overhead. The DMA regularization is simple, efficient, and effective. Therefore, it can be used as a basic regularization method for models based on neural networks. We evaluate DMA by applying it to various modern models on CIFAR10, CIFAR100, and TinyImageNet datasets, decreasing the test error rate by 0.2-0.4%, 0.2-1.5%, and 0.3-0.4% respectively. Code is available at: https://github.com/wznpub/DMA_Regularization.

Capsule projection network (CapProNet) has shown its ability to obtain semantic information, and spatial structural information from the raw images. However, the vector capsule of CapProNet has limitations in representing semantic information due to ignoring local information. Besides, the number of trainable parameters also increases greatly with the dimension of the feature vector. To that end, we propose a matrix capsule convolution projection (MCCP) module by replacing the feature vector with a feature matrix, of which each column represents a local feature. The feature matrix is then convoluted by columns into capsule subspaces to decrease the number of trainable parameters effectively. Furthermore, the CapDetNet is designed to explore the structural information encoding of the MCCP module based on object detection task. Experimental results demonstrate that the proposed MCCP outperforms the baselines in image classification, and CapDetNet achieves the 2.3% performance gain in object detection.

In this paper, we analyze the inner product of weight vector w and data vector x in neural networks from the perspective of vector orthogonal decomposition and prove that the direction gradient of w decreases with the angle between them close to 0 or π. We propose the Projection and Rejection Product (PR Product) to make the direction gradient of w independent of the angle and consistently larger than the one in standard inner product while keeping the forward propagation identical. As a reliable substitute for standard inner product, the PR Product can be applied into many existing deep learning modules, so we develop the PR Product version of fully connected layer, convolutional layer and LSTM layer. In static image classification, the experiments on CIFAR10 and CIFAR100 datasets demonstrate that the PR Product can robustly enhance the ability of various state-of-the-art classification networks. On the task of image captioning, even without any bells and whistles, our PR Product version of captioning model can compete or outperform the state-of-the-art models on MS COCO dataset. Code has been made available at: https://github.com/wzn0828/PR_Product.