Abstract Most recent learning algorithms for single image dehazing are designed to train with paired hazy and corresponding ground truth images, typically synthesized images. Real paired datasets can help to improve performance, but are tough to acquire. This paper proposes an unsupervised dehazing algorithm based on GAN to alleviate this issue. An end-to-end network based on GAN architecture is established and fed with unpaired clean and hazy images, signifying that the estimation of atmospheric light and transmission is not required. The proposed network consists of three parts: a generator, a global test discriminator, and a local context discriminator. Moreover, a dark channel prior based attention mechanism is applied to handle inconsistency haze. We conduct experiments on RESIDE datasets. Extensive experiments demonstrated the effectiveness of the proposed approach which outperformed previous state-of-the-art unsupervised methods by a large margin.

Few-Shot Image Classification aims to identify unseen categories by a limited number of instances. Recently, some metric-based methods have attempted to generate more discriminative task-specific embeddings by embedding adaptation strategies. However, the generated embeddings are either query-agnostic or ignore local relations between instances in each category, resulting in limited performance improvement. To address the above issues, in this letter, we propose QS-CAN, a Query-Specific embedding Co-Adaptation Network, which generates task- and query-specific embeddings by fusing inter-class and intra-class information. The core modules of QS-CAN are Inter-Class Adapter(Inter-A) and Intra-Class Adapter(Intra-A). The Inter-Class Adapter encodes the global relationship within the task, pushing the different categories away from each other. At the same time, the Intra-Class Adapter focuses on modeling the local relationship within each category, pulling the instances within a category closer. Moreover, an Adaptive Fusion Module(AFM) is proposed to integrate two co-adapted embeddings to get a more discriminative space. Experiments show that our method performs comparably to other advanced methods on three widely used datasets.

Few-shot image classification (FSIC) is the task of generalizing a model to unknown categories by learning from a small number of labeled samples of some given categories. Recently, metric-based approaches have received lots of attention for their simplicity and effectiveness, but they often only use support set to generate inaccurate prototypes matching query set, ignoring the rich information contained in queries and the reversibility of the matching relationship between the two. In this letter, we propose a new simple and effective metric-based method called Bidirectional Matching Prototypical Network (BMPN), which has three innovations:1)It has an additional reverse matching process. This process uses queries to generate more accurate prototypes to improve the model’s performance while also forcing the model to learn features far from the decision boundary to enhance generalization capabilities; 2)It has a lightweight coordinate attention feature extractor (CAFE). This module not only captures long-term dependence along one spatial direction but also saving the accurate position information of the other spatial direction, helping the model to locate the region of interest more accurately; 3)It has a joint loss function, including forward matching loss and reverse matching loss, and a progressive weighting strategy is used in the training process to balance the importance of the two. Our model is trained end-to-end, and the experimental results show that we have reached the most advanced performance on the two benchmark datasets.

This paper proposed a THPHP (Task-based Hybrid Parallels and Hybrid Pipelines) scheme to implement multistandard video decoding algorithms, i.e. MPEG-2, H.264 and AVS (Audio Video coding Standard), on a heterogeneous coarsegrained reconfigurable multimedia processor called REMUS (REconfigurable MUltimedia System). Multiple level parallelism and multiple level pipeline techniques are proposed in this scheme. Simulation results show that the video decoder can support H.264 HP (High Profile) 1920×1080@30fps (frame per second) streams, AVS JP (Jizhun Profile) 1920×1080@39fps streams, and MPEG-2 MP (Main Profile) 1920×1080@41fps streams when exploiting a 200MHz working frequency.