High-resolution representations are essential for position-sensitive vision problems, such as human pose estimation, semantic segmentation, and object detection. Existing state-of-the-art frameworks first encode the input image as a low-resolution representation through a subnetwork that is formed by connecting high-to-low resolution convolutions in series (e.g., ResNet, VGGNet), and then recover the high-resolution representation from the encoded low-resolution representation. Instead, our proposed network, named as High-Resolution Network (HRNet), maintains high-resolution representations through the whole process. There are two key characteristics: (i) Connect the high-to-low resolution convolution streams in parallel; (ii) Repeatedly exchange the information across resolutions. The benefit is that the resulting representation is semantically richer and spatially more precise. We show the superiority of the proposed HRNet in a wide range of applications, including human pose estimation, semantic segmentation, and object detection, suggesting that the HRNet is a stronger backbone for computer vision problems. All the codes are available at https://github.com/HRNet.

Deep learning based medical image diagnosis has shown great potential in clinical medicine. However, it often suffers two major difficulties in real-world applications: 1) only limited labels are available for model training, due to expensive annotation costs over medical images; 2) labeled images may contain considerable label noise (e.g., mislabeling labels) due to diagnostic difficulties of diseases. To address these, we seek to exploit rich labeled data from relevant domains to help the learning in the target task via Unsupervised Domain Adaptation (UDA). Unlike most UDA methods that rely on clean labeled data or assume samples are equally transferable, we innovatively propose a Collaborative Unsupervised Domain Adaptation algorithm, which conducts transferability-aware adaptation and conquers label noise in a collaborative way. We theoretically analyze the generalization performance of the proposed method, and also empirically evaluate it on both medical and general images. Promising experimental results demonstrate the superiority and generalization of the proposed method.

We study network pruning which aims to remove redundant channels/kernels and accelerate the inference of deep networks. Existing pruning methods either train from scratch with sparsity constraints or minimize the reconstruction error between the feature maps of the pre-trained models and the compressed ones. Both strategies suffer from some limitations: the former kind is computationally expensive and difficult to converge, while the latter kind optimizes the reconstruction error but ignores the discriminative power of channels. In this paper, we propose a discrimination-aware channel pruning (DCP) method to choose the channels that actually contribute to the discriminative power. Based on DCP, we further propose several techniques to improve the optimization efficiency. Note that the parameters of a channel (3D tensor) may contain redundant kernels (each with a 2D matrix). To solve this issue, we propose a discrimination-aware kernel pruning (DKP) method to select the kernels with promising discriminative power. Experiments on image classification and face recognition demonstrate the effectiveness of our methods. For example, on ILSVRC-12, the resultant ResNet-50 with 30% reduction of channels even outperforms the baseline model by 0.36% on Top-1 accuracy. The pruned MobileNetV1 and MobileNetV2 achieve 1.93x and 1.42x inference acceleration on a mobile device, respectively, with negligible performance degradation.

We focus on the task of generating sound from natural videos, and the sound should be both temporally and content-wise aligned with visual signals. This task is extremely challenging because some sounds generated outside a camera can not be inferred from video content. The model may be forced to learn an incorrect mapping between visual content and these irrelevant sounds. To address this challenge, we propose a framework named REGNET. In this framework, we first extract appearance and motion features from video frames to better distinguish the object that emits sound from complex background information. We then introduce an innovative audio forwarding regularizer that directly considers the real sound as input and outputs bottlenecked sound features. Using both visual and bottlenecked sound features for sound prediction during training provides stronger supervision for the sound prediction. The audio forwarding regularizer can control the irrelevant sound component and thus prevent the model from learning an incorrect mapping between video frames and sound emitted by the object that is out of the screen. During testing, the audio forwarding regularizer is removed to ensure that REGNET can produce purely aligned sound only from visual features. Extensive evaluations based on Amazon Mechanical Turk demonstrate that our method significantly improves both temporal and contentwise alignment. Remarkably, our generated sound can fool the human with a 68.12% success rate. Code and pre-trained models are publicly available at https://github.com/PeihaoChen/regnet.

We address the challenging problem of weakly supervised temporal action localization from unconstrained web videos, where only the video-level action labels are available during training. Inspired by the Adversarial Erasing strategy in weakly supervised semantic segmentation, we propose a novel iterative-winners-out network. Specifically, we make two technical contributions: 1) we propose an iterative training strategy, namely winners-out, to select the most discriminative action instances in each training iteration and remove them in the next training iteration. This iterative process alleviates the “winner-takes-all” phenomenon that existing approaches tend to choose the video segments that strongly correspond to the video label, but neglect other less discriminative video segments. With this strategy, our network is able to localize not only the most discriminative instances but also the less discriminative ones. 2) to better select the target action instances in winners-out, we devise a class-discriminative localization technique. By employing the attention mechanism and the information learned from data, our technique is able to identify the most discriminative action instances effectively. The two key components are integrated into an end-to-end network to localize actions without using the frame-level annotations. Extensive experimental results demonstrate that our method outperforms the state-of-the-art weakly supervised approaches on ActivityNet1.3 and improves mAP from 16.9% to 20.5% on THUMOS14. Notably, even with weak video-level supervision, our method attains comparable accuracy to those employing frame-level supervisions.