Colonoscopic video retrieval, which is a critical part of polyp treatment, has great clinical significance for the prevention and treatment of colorectal cancer. However, retrieval models trained on action recognition datasets usually produce unsatisfactory retrieval results on colonoscopic datasets due to the large domain gap between them. To seek a solution to this problem, we construct a large-scale colonoscopic dataset named Colo-Pair for medical practice. Based on this dataset, a simple yet effective training method called Colo-SCRL is proposed for more robust representation learning. It aims to refine general knowledge from colonoscopies through masked autoencoder-based reconstruction and momentum contrast to improve retrieval performance. To the best of our knowledge, this is the first attempt to employ the contrastive learning paradigm for medical video retrieval. Empirical results show that our method significantly outperforms current state-of-the-art methods in the colonoscopic video retrieval task.
Graph augmentations are essential for graph contrastive learning. Most existing works use pre-defined random augmentations, which are usually unable to adapt to different input graphs and fail to consider the impact of different nodes and edges on graph semantics. To address this issue, we propose a framework called Hybrid Augmented Automated Graph Contrastive Learning (HAGCL). HAGCL consists of a feature-level learnable view generator and an edge-level learnable view generator. The view generators are end-to-end differentiable to learn the probability distribution of views conditioned on the input graph. It insures to learn the most semantically meaningful structure in terms of features and topology, respectively. Furthermore, we propose an improved joint training strategy, which can achieve better results than previous works without resorting to any weak label information in the downstream tasks and extensive evaluation of additional work.
Contrastive learning-based vision-language pre-training approaches, such as CLIP, have demonstrated great success in many vision-language tasks. These methods achieve cross-modal alignment by encoding a matched image-text pair with similar feature embeddings, which are generated by aggregating information from visual patches and language tokens. However, direct aligning cross-modal information using such representations is challenging, as visual patches and text tokens differ in semantic levels and granularities. To alleviate this issue, we propose a Finite Discrete Tokens (FDT) based multimodal representation. FDT is a set of learnable tokens representing certain visual-semantic concepts. Both images and texts are embedded using shared FDT by first grounding multimodal inputs to FDT space and then aggregating the activated FDT representations. The matched visual and semantic concepts are enforced to be represented by the same set of discrete tokens by a sparse activation constraint. As a result, the granularity gap between the two modalities is reduced. Through both quantitative and qualitative analyses, we demonstrate that using FDT representations in CLIP-style models improves cross-modal alignment and performance in visual recognition and vision-language downstream tasks. Furthermore, we show that our method can learn more comprehensive representations, and the learned FDT capture meaningful cross-modal correspondence, ranging from objects to actions and attributes.
The automatic generation of stylized co-speech gestures has recently received increasing attention. Previous systems typically allow style control via predefined text labels or example motion clips, which are often not flexible enough to convey user intent accurately. In this work, we present GestureDiffuCLIP, a neural network framework for synthesizing realistic, stylized co-speech gestures with flexible style control. We leverage the power of the large-scale Contrastive-Language-Image-Pre-training (CLIP) model and present a novel CLIP-guided mechanism that extracts efficient style representations from multiple input modalities, such as a piece of text, an example motion clip, or a video. Our system learns a latent diffusion model to generate high-quality gestures and infuses the CLIP representations of style into the generator via an adaptive instance normalization (AdaIN) layer. We further devise a gesture-transcript alignment mechanism that ensures a semantically correct gesture generation based on contrastive learning. Our system can also be extended to allow fine-grained style control of individual body parts. We demonstrate an extensive set of examples showing the flexibility and generalizability of our model to a variety of style descriptions. In a user study, we show that our system outperforms the state-of-the-art approaches regarding human likeness, appropriateness, and style correctness.
We introduce Deep Augmentation, an approach to implicit data augmentation using dropout or PCA to transform a targeted layer within a neural network to improve performance and generalization. We demonstrate Deep Augmentation through extensive experiments on contrastive learning tasks in NLP, computer vision, and graph learning. We observe substantial performance gains with Transformers, ResNets, and Graph Neural Networks as the underlying models in contrastive learning, but observe inverse effects on the corresponding supervised problems. Our analysis suggests that Deep Augmentation alleviates co-adaptation between layers, a problem exhibited by self-supervised learning where ground truth labels are not available. We use this observation to formulate a method for selecting which layer to target; in particular, our experimentation reveals that targeting deeper layers with Deep Augmentation outperforms augmenting the input data. The simple network- and modality-agnostic nature of this approach enables its integration into various machine learning pipelines.
Effective modeling of complex spatiotemporal dependencies in long-form videos remains an open problem. The recently proposed Structured State-Space Sequence (S4) model with its linear complexity offers a promising direction in this space. However, we demonstrate that treating all image-tokens equally as done by S4 model can adversely affect its efficiency and accuracy. To address this limitation, we present a novel Selective S4 (i.e., S5) model that employs a lightweight mask generator to adaptively select informative image tokens resulting in more efficient and accurate modeling of long-term spatiotemporal dependencies in videos. Unlike previous mask-based token reduction methods used in transformers, our S5 model avoids the dense self-attention calculation by making use of the guidance of the momentum-updated S4 model. This enables our model to efficiently discard less informative tokens and adapt to various long-form video understanding tasks more effectively. However, as is the case for most token reduction methods, the informative image tokens could be dropped incorrectly. To improve the robustness and the temporal horizon of our model, we propose a novel long-short masked contrastive learning (LSMCL) approach that enables our model to predict longer temporal context using shorter input videos. We present extensive comparative results using three challenging long-form video understanding datasets (LVU, COIN and Breakfast), demonstrating that our approach consistently outperforms the previous state-of-the-art S4 model by up to 9.6% accuracy while reducing its memory footprint by 23%.
Active learning aims to identify the most informative data from an unlabeled data pool that enables a model to reach the desired accuracy rapidly. This benefits especially deep neural networks which generally require a huge number of labeled samples to achieve high performance. Most existing active learning methods have been evaluated in an ideal setting where only samples relevant to the target task, i.e., in-distribution samples, exist in an unlabeled data pool. A data pool gathered from the wild, however, is likely to include samples that are irrelevant to the target task at all and/or too ambiguous to assign a single class label even for the oracle. We argue that assuming an unlabeled data pool consisting of samples from various distributions is more realistic. In this work, we introduce new active learning benchmarks that include ambiguous, task-irrelevant out-of-distribution as well as in-distribution samples. We also propose an active learning method designed to acquire informative in-distribution samples in priority. The proposed method leverages both labeled and unlabeled data pools and selects samples from clusters on the feature space constructed via contrastive learning. Experimental results demonstrate that the proposed method requires a lower annotation budget than existing active learning methods to reach the same level of accuracy.
Recently, a growing number of work design unsupervised paradigms for point cloud processing to alleviate the limitation of expensive manual annotation and poor transferability of supervised methods. Among them, CrossPoint follows the contrastive learning framework and exploits image and point cloud data for unsupervised point cloud understanding. Although the promising performance is presented, the unbalanced architecture makes it unnecessarily complex and inefficient. For example, the image branch in CrossPoint is $\sim$8.3x heavier than the point cloud branch leading to higher complexity and latency. To address this problem, in this paper, we propose a lightweight Vision-and-Pointcloud Transformer (ViPFormer) to unify image and point cloud processing in a single architecture. ViPFormer learns in an unsupervised manner by optimizing intra-modal and cross-modal contrastive objectives. Then the pretrained model is transferred to various downstream tasks, including 3D shape classification and semantic segmentation. Experiments on different datasets show ViPFormer surpasses previous state-of-the-art unsupervised methods with higher accuracy, lower model complexity and runtime latency. Finally, the effectiveness of each component in ViPFormer is validated by extensive ablation studies. The implementation of the proposed method is available at https://github.com/auniquesun/ViPFormer.
Unsupervised Domain Adaptation (UDA) of semantic segmentation transfers labeled source knowledge to an unlabeled target domain by relying on accessing both the source and target data. However, the access to source data is often restricted or infeasible in real-world scenarios. Under the source data restrictive circumstances, UDA is less practical. To address this, recent works have explored solutions under the Source-Free Domain Adaptation (SFDA) setup, which aims to adapt a source-trained model to the target domain without accessing source data. Still, existing SFDA approaches use only image-level information for adaptation, making them sub-optimal in video applications. This paper studies SFDA for Video Semantic Segmentation (VSS), where temporal information is leveraged to address video adaptation. Specifically, we propose Spatio-Temporal Pixel-Level (STPL) contrastive learning, a novel method that takes full advantage of spatio-temporal information to tackle the absence of source data better. STPL explicitly learns semantic correlations among pixels in the spatio-temporal space, providing strong self-supervision for adaptation to the unlabeled target domain. Extensive experiments show that STPL achieves state-of-the-art performance on VSS benchmarks compared to current UDA and SFDA approaches. Code is available at: https://github.com/shaoyuanlo/STPL
Microscopy images often suffer from high levels of noise, which can hinder further analysis and interpretation. Content-aware image restoration (CARE) methods have been proposed to address this issue, but they often require large amounts of training data and suffer from over-fitting. To overcome these challenges, we propose a novel framework for few-shot microscopy image denoising. Our approach combines a generative adversarial network (GAN) trained via contrastive learning (CL) with two structure preserving loss terms (Structural Similarity Index and Total Variation loss) to further improve the quality of the denoised images using little data. We demonstrate the effectiveness of our method on three well-known microscopy imaging datasets, and show that we can drastically reduce the amount of training data while retaining the quality of the denoising, thus alleviating the burden of acquiring paired data and enabling few-shot learning. The proposed framework can be easily extended to other image restoration tasks and has the potential to significantly advance the field of microscopy image analysis.
Natural videos captured by consumer cameras often suffer from low framerate and motion blur due to the combination of dynamic scene complexity, lens and sensor imperfection, and less than ideal exposure setting. As a result, computational methods that jointly perform video frame interpolation and deblurring begin to emerge with the unrealistic assumption that the exposure time is known and fixed. In this work, we aim ambitiously for a more realistic and challenging task - joint video multi-frame interpolation and deblurring under unknown exposure time. Toward this goal, we first adopt a variant of supervised contrastive learning to construct an exposure-aware representation from input blurred frames. We then train two U-Nets for intra-motion and inter-motion analysis, respectively, adapting to the learned exposure representation via gain tuning. We finally build our video reconstruction network upon the exposure and motion representation by progressive exposure-adaptive convolution and motion refinement. Extensive experiments on both simulated and real-world datasets show that our optimized method achieves notable performance gains over the state-of-the-art on the joint video x8 interpolation and deblurring task. Moreover, on the seemingly implausible x16 interpolation task, our method outperforms existing methods by more than 1.5 dB in terms of PSNR.
Dramatic demand for manpower to label pixel-level annotations triggered the advent of unsupervised semantic segmentation. Although the recent work employing the vision transformer (ViT) backbone shows exceptional performance, there is still a lack of consideration for task-specific training guidance and local semantic consistency. To tackle these issues, we leverage contrastive learning by excavating hidden positives to learn rich semantic relationships and ensure semantic consistency in local regions. Specifically, we first discover two types of global hidden positives, task-agnostic and task-specific ones for each anchor based on the feature similarities defined by a fixed pre-trained backbone and a segmentation head-in-training, respectively. A gradual increase in the contribution of the latter induces the model to capture task-specific semantic features. In addition, we introduce a gradient propagation strategy to learn semantic consistency between adjacent patches, under the inherent premise that nearby patches are highly likely to possess the same semantics. Specifically, we add the loss propagating to local hidden positives, semantically similar nearby patches, in proportion to the predefined similarity scores. With these training schemes, our proposed method achieves new state-of-the-art (SOTA) results in COCO-stuff, Cityscapes, and Potsdam-3 datasets. Our code is available at: https://github.com/hynnsk/HP.
This paper presents Contrastive Transformer, a contrastive learning scheme using the Transformer innate patches. Contrastive Transformer enables existing contrastive learning techniques, often used for image classification, to benefit dense downstream prediction tasks such as semantic segmentation. The scheme performs supervised patch-level contrastive learning, selecting the patches based on the ground truth mask, subsequently used for hard-negative and hard-positive sampling. The scheme applies to all vision-transformer architectures, is easy to implement, and introduces minimal additional memory footprint. Additionally, the scheme removes the need for huge batch sizes, as each patch is treated as an image. We apply and test Contrastive Transformer for the case of aerial image segmentation, known for low-resolution data, large class imbalance, and similar semantic classes. We perform extensive experiments to show the efficacy of the Contrastive Transformer scheme on the ISPRS Potsdam aerial image segmentation dataset. Additionally, we show the generalizability of our scheme by applying it to multiple inherently different Transformer architectures. Ultimately, the results show a consistent increase in mean IoU across all classes.
We propose a simple pairwise Sigmoid loss for Language-Image Pre-training (SigLIP). Unlike standard contrastive learning with softmax normalization, the sigmoid loss operates solely on image-text pairs and does not require a global view of the pairwise similarities for normalization. The sigmoid loss simultaneously allows further scaling up the batch size, while also performing better at smaller batch sizes. Combined with Locked-image Tuning, with only four TPUv4 chips, we train a SigLiT model that achieves 84.5% ImageNet zero-shot accuracy in two days. The disentanglement of the batch size from the loss further allows us to study the impact of examples vs pairs and negative to positive ratio. Finally, we push the batch size to the extreme, up to one million, and find that the benefits of growing batch size quickly diminish, with a more reasonable batch size of 32k being sufficient. We release our models at https://github.com/google-research/big_vision and hope our research motivates further explorations in improving the quality and efficiency of language-image pre-training.
The excellent generative capabilities of text-to-image diffusion models suggest they learn informative representations of image-text data. However, what knowledge their representations capture is not fully understood, and they have not been thoroughly explored on downstream tasks. We investigate diffusion models by proposing a method for evaluating them as zero-shot classifiers. The key idea is using a diffusion model's ability to denoise a noised image given a text description of a label as a proxy for that label's likelihood. We apply our method to Stable Diffusion and Imagen, using it to probe fine-grained aspects of the models' knowledge and comparing them with CLIP's zero-shot abilities. They perform competitively with CLIP on a wide range of zero-shot image classification datasets. Additionally, they achieve state-of-the-art results on shape/texture bias tests and can successfully perform attribute binding while CLIP cannot. Although generative pre-training is prevalent in NLP, visual foundation models often use other methods such as contrastive learning. Based on our findings, we argue that generative pre-training should be explored as a compelling alternative for vision-language tasks.
Contrastive learning is a powerful self-supervised learning method, but we have a limited theoretical understanding of how it works and why it works. In this paper, we prove that contrastive learning with the standard InfoNCE loss is equivalent to spectral clustering on the similarity graph. Using this equivalence as the building block, we extend our analysis to the CLIP model and rigorously characterize how similar multi-modal objects are embedded together. Motivated by our theoretical insights, we introduce the Kernel-InfoNCE loss, incorporating mixtures of kernel functions that outperform the standard Gaussian kernel on several vision datasets. The code is available at https://github.com/yifanzhang-pro/Kernel-InfoNCE.
Contrastive learning-based video-language representation learning approaches, e.g., CLIP, have achieved outstanding performance, which pursue semantic interaction upon pre-defined video-text pairs. To clarify this coarse-grained global interaction and move a step further, we have to encounter challenging shell-breaking interactions for fine-grained cross-modal learning. In this paper, we creatively model video-text as game players with multivariate cooperative game theory to wisely handle the uncertainty during fine-grained semantic interaction with diverse granularity, flexible combination, and vague intensity. Concretely, we propose Hierarchical Banzhaf Interaction (HBI) to value possible correspondence between video frames and text words for sensitive and explainable cross-modal contrast. To efficiently realize the cooperative game of multiple video frames and multiple text words, the proposed method clusters the original video frames (text words) and computes the Banzhaf Interaction between the merged tokens. By stacking token merge modules, we achieve cooperative games at different semantic levels. Extensive experiments on commonly used text-video retrieval and video-question answering benchmarks with superior performances justify the efficacy of our HBI. More encouragingly, it can also serve as a visualization tool to promote the understanding of cross-modal interaction, which have a far-reaching impact on the community. Project page is available at https://jpthu17.github.io/HBI/.
Most self-supervised methods for representation learning leverage a cross-view consistency objective i.e., they maximize the representation similarity of a given image's augmented views. Recent work NNCLR goes beyond the cross-view paradigm and uses positive pairs from different images obtained via nearest neighbor bootstrapping in a contrastive setting. We empirically show that as opposed to the contrastive learning setting which relies on negative samples, incorporating nearest neighbor bootstrapping in a self-distillation scheme can lead to a performance drop or even collapse. We scrutinize the reason for this unexpected behavior and provide a solution. We propose to adaptively bootstrap neighbors based on the estimated quality of the latent space. We report consistent improvements compared to the naive bootstrapping approach and the original baselines. Our approach leads to performance improvements for various self-distillation method/backbone combinations and standard downstream tasks. Our code is publicly available at https://github.com/tileb1/AdaSim.
Multimodal alignment facilitates the retrieval of instances from one modality when queried using another. In this paper, we consider a novel setting where such an alignment is between (i) instruction steps that are depicted as assembly diagrams (commonly seen in Ikea assembly manuals) and (ii) video segments from in-the-wild videos; these videos comprising an enactment of the assembly actions in the real world. To learn this alignment, we introduce a novel supervised contrastive learning method that learns to align videos with the subtle details in the assembly diagrams, guided by a set of novel losses. To study this problem and demonstrate the effectiveness of our method, we introduce a novel dataset: IAW for Ikea assembly in the wild consisting of 183 hours of videos from diverse furniture assembly collections and nearly 8,300 illustrations from their associated instruction manuals and annotated for their ground truth alignments. We define two tasks on this dataset: First, nearest neighbor retrieval between video segments and illustrations, and, second, alignment of instruction steps and the segments for each video. Extensive experiments on IAW demonstrate superior performances of our approach against alternatives.
Adverse weather removal tasks like deraining, desnowing, and dehazing are usually treated as separate tasks. However, in practical autonomous driving scenarios, the type, intensity,and mixing degree of weather are unknown, so handling each task separately cannot deal with the complex practical scenarios. In this paper, we study the blind adverse weather removal problem. Mixture-of-Experts (MoE) is a popular model that adopts a learnable gate to route the input to different expert networks. The principle of MoE involves using adaptive networks to process different types of unknown inputs. Therefore, MoE has great potential for blind adverse weather removal. However, the original MoE module is inadequate for coupled multiple weather types and fails to utilize multi-scale features for better performance. To this end, we propose a method called Weather-aware Multi-scale MoE (WM-MoE) based on Transformer for blind weather removal. WM-MoE includes two key designs: WEather-Aware Router (WEAR) and Multi-Scale Experts (MSE). WEAR assigns experts for each image token based on decoupled content and weather features, which enhances the model's capability to process multiple adverse weathers. To obtain discriminative weather features from images, we propose Weather Guidance Fine-grained Contrastive Learning (WGF-CL), which utilizes weather cluster information to guide the assignment of positive and negative samples for each image token. Since processing different weather types requires different receptive fields, MSE leverages multi-scale features to enhance the spatial relationship modeling capability, facilitating the high-quality restoration of diverse weather types and intensities. Our method achieves state-of-the-art performance in blind adverse weather removal on two public datasets and our dataset. We also demonstrate the advantage of our method on downstream segmentation tasks.