Self-supervised learning (SSL) has made enormous progress and largely narrowed the gap with the supervised ones, where the representation learning is mainly guided by a projection into an embedding space. During the projection, current methods simply adopt uniform aggregation of pixels for embedding; however, this risks involving object-irrelevant nuisances and spatial misalignment for different augmentations. In this paper, we present a new approach, Learning Where to Learn (LEWEL), to adaptively aggregate spatial information of features, so that the projected embeddings could be exactly aligned and thus guide the feature learning better. Concretely, we reinterpret the projection head in SSL as a per-pixel projection and predict a set of spatial alignment maps from the original features by this weight-sharing projection head. A spectrum of aligned embeddings is thus obtained by aggregating the features with spatial weighting according to these alignment maps. As a result of this adaptive alignment, we observe substantial improvements on both image-level prediction and dense prediction at the same time: LEWEL improves MoCov2 by 1.6%/1.3%/0.5%/0.4% points, improves BYOL by 1.3%/1.3%/0.7%/0.6% points, on ImageNet linear/semi-supervised classification, Pascal VOC semantic segmentation, and object detection, respectively.
Neural volume rendering has been proven to be a promising method for efficient and photo-realistic rendering of a human performer in free-view, a critical task in many immersive VR/AR applications. However, existing approaches are severely limited by their high computational cost in the rendering process. To solve this problem, we propose the UV Volumes, an approach that can render an editable free-view video of a human performer in real-time. It is achieved by removing the high-frequency (i.e., non-smooth) human textures from the 3D volume and encoding them into a 2D neural texture stack (NTS). The smooth UV volume allows us to employ a much smaller and shallower structure for 3D CNN and MLP, to obtain the density and texture coordinates without losing image details. Meanwhile, the NTS only needs to be queried once for each pixel in the UV image to retrieve its RGB value. For editability, the 3D CNN and MLP decoder can easily fit the function that maps the input structured-and-posed latent codes to the relatively smooth densities and texture coordinates. It gives our model a better generalization ability to handle novel poses and shapes. Furthermore, the use of NST enables new applications, e.g., retexturing. Extensive experiments on CMU Panoptic, ZJU Mocap, and H36M datasets show that our model can render 900 * 500 images in 40 fps on average with comparable photorealism to state-of-the-art methods. The project and supplementary materials are available at https://fanegg.github.io/UV-Volumes.
Searching for a more compact network width recently serves as an effective way of channel pruning for the deployment of convolutional neural networks (CNNs) under hardware constraints. To fulfill the searching, a one-shot supernet is usually leveraged to efficiently evaluate the performance \wrt~different network widths. However, current methods mainly follow a \textit{unilaterally augmented} (UA) principle for the evaluation of each width, which induces the training unfairness of channels in supernet. In this paper, we introduce a new supernet called Bilaterally Coupled Network (BCNet) to address this issue. In BCNet, each channel is fairly trained and responsible for the same amount of network widths, thus each network width can be evaluated more accurately. Besides, we propose to reduce the redundant search space and present the BCNetV2 as the enhanced supernet to ensure rigorous training fairness over channels. Furthermore, we leverage a stochastic complementary strategy for training the BCNet, and propose a prior initial population sampling method to boost the performance of the evolutionary search. We also propose the first open-source width benchmark on macro structures named Channel-Bench-Macro for the better comparison of width search algorithms. Extensive experiments on benchmark CIFAR-10 and ImageNet datasets indicate that our method can achieve state-of-the-art or competing performance over other baseline methods. Moreover, our method turns out to further boost the performance of NAS models by refining their network widths. For example, with the same FLOPs budget, our obtained EfficientNet-B0 achieves 77.53\% Top-1 accuracy on ImageNet dataset, surpassing the performance of original setting by 0.65\%.
Structural re-parameterization (Rep) methods achieve noticeable improvements on simple VGG-style networks. Despite the prevalence, current Rep methods simply re-parameterize all operations into an augmented network, including those that rarely contribute to the model's performance. As such, the price to pay is an expensive computational overhead to manipulate these unnecessary behaviors. To eliminate the above caveats, we aim to bootstrap the training with minimal cost by devising a dynamic re-parameterization (DyRep) method, which encodes Rep technique into the training process that dynamically evolves the network structures. Concretely, our proposal adaptively finds the operations which contribute most to the loss in the network, and applies Rep to enhance their representational capacity. Besides, to suppress the noisy and redundant operations introduced by Rep, we devise a de-parameterization technique for a more compact re-parameterization. With this regard, DyRep is more efficient than Rep since it smoothly evolves the given network instead of constructing an over-parameterized network. Experimental results demonstrate our effectiveness, e.g., DyRep improves the accuracy of ResNet-18 by $2.04\%$ on ImageNet and reduces $22\%$ runtime over the baseline. Code is available at: https://github.com/hunto/DyRep.
Learning with few labeled data has been a longstanding problem in the computer vision and machine learning research community. In this paper, we introduced a new semi-supervised learning framework, SimMatch, which simultaneously considers semantic similarity and instance similarity. In SimMatch, the consistency regularization will be applied on both semantic-level and instance-level. The different augmented views of the same instance are encouraged to have the same class prediction and similar similarity relationship respected to other instances. Next, we instantiated a labeled memory buffer to fully leverage the ground truth labels on instance-level and bridge the gaps between the semantic and instance similarities. Finally, we proposed the \textit{unfolding} and \textit{aggregation} operation which allows these two similarities be isomorphically transformed with each other. In this way, the semantic and instance pseudo-labels can be mutually propagated to generate more high-quality and reliable matching targets. Extensive experimental results demonstrate that SimMatch improves the performance of semi-supervised learning tasks across different benchmark datasets and different settings. Notably, with 400 epochs of training, SimMatch achieves 67.2\%, and 74.4\% Top-1 Accuracy with 1\% and 10\% labeled examples on ImageNet, which significantly outperforms the baseline methods and is better than previous semi-supervised learning frameworks. Code and pre-trained models are available at https://github.com/KyleZheng1997/simmatch.
Self-supervised Learning (SSL) including the mainstream contrastive learning has achieved great success in learning visual representations without data annotations. However, most methods mainly focus on the instance level information (\ie, the different augmented images of the same instance should have the same feature or cluster into the same class), but there is a lack of attention on the relationships between different instances. In this paper, we introduce a novel SSL paradigm, which we term as relational self-supervised learning (ReSSL) framework that learns representations by modeling the relationship between different instances. Specifically, our proposed method employs sharpened distribution of pairwise similarities among different instances as \textit{relation} metric, which is thus utilized to match the feature embeddings of different augmentations. To boost the performance, we argue that weak augmentations matter to represent a more reliable relation, and leverage momentum strategy for practical efficiency. The designed asymmetric predictor head and an InfoNCE warm-up strategy enhance the robustness to hyper-parameters and benefit the resulting performance. Experimental results show that our proposed ReSSL substantially outperforms the state-of-the-art methods across different network architectures, including various lightweight networks (\eg, EfficientNet and MobileNet).
This paper seeks to provide the information retrieval community with some reflections on the current improvements of retrieval learning through the analysis of the reproducibility aspects of image-text retrieval models. For the latter part of the past decade, image-text retrieval has gradually become a major research direction in the field of information retrieval because of the growth of multi-modal data. Many researchers use benchmark datasets like MS-COCO and Flickr30k to train and assess the performance of image-text retrieval algorithms. Research in the past has mostly focused on performance, with several state-of-the-art methods being proposed in various ways. According to their claims, these approaches achieve better modal interactions and thus better multimodal representations with greater precision. In contrast to those previous works, we focus on the repeatability of the approaches and the overall examination of the elements that lead to improved performance by pretrained and nonpretrained models in retrieving images and text. To be more specific, we first examine the related reproducibility concerns and why the focus is on image-text retrieval tasks, and then we systematically summarize the current paradigm of image-text retrieval models and the stated contributions of those approaches. Second, we analyze various aspects of the reproduction of pretrained and nonpretrained retrieval models. Based on this, we conducted ablation experiments and obtained some influencing factors that affect retrieval recall more than the improvement claimed in the original paper. Finally, we also present some reflections and issues that should be considered by the retrieval community in the future. Our code is freely available at https://github.com/WangFei-2019/Image-text-Retrieval.
Low-dose computed tomography (LDCT) denoising is an important problem in CT research. Compared to the normal dose CT (NDCT), LDCT images are subjected to severe noise and artifacts. Recently in many studies, vision transformers have shown superior feature representation ability over convolutional neural networks (CNNs). However, unlike CNNs, the potential of vision transformers in LDCT denoising was little explored so far. To fill this gap, we propose a Convolution-free Token2Token Dilated Vision Transformer for low-dose CT denoising. The CTformer uses a more powerful token rearrangement to encompass local contextual information and thus avoids convolution. It also dilates and shifts feature maps to capture longer-range interaction. We interpret the CTformer by statically inspecting patterns of its internal attention maps and dynamically tracing the hierarchical attention flow with an explanatory graph. Furthermore, an overlapped inference mechanism is introduced to effectively eliminate the boundary artifacts that are common for encoder-decoder-based denoising models. Experimental results on Mayo LDCT dataset suggest that the CTformer outperforms the state-of-the-art denoising methods with a low computation overhead.
Evaluation metrics in machine learning are often hardly taken as loss functions, as they could be non-differentiable and non-decomposable, e.g., average precision and F1 score. This paper aims to address this problem by revisiting the surrogate loss learning, where a deep neural network is employed to approximate the evaluation metrics. Instead of pursuing an exact recovery of the evaluation metric through a deep neural network, we are reminded of the purpose of the existence of these evaluation metrics, which is to distinguish whether one model is better or worse than another. In this paper, we show that directly maintaining the relation of models between surrogate losses and metrics suffices, and propose a rank correlation-based optimization method to maximize this relation and learn surrogate losses. Compared to previous works, our method is much easier to optimize and enjoys significant efficiency and performance gains. Extensive experiments show that our method achieves improvements on various tasks including image classification and neural machine translation, and even outperforms state-of-the-art methods on human pose estimation and machine reading comprehension tasks. Code is available at: https://github.com/hunto/ReLoss.