GCNet: Non-Local Networks Meet Squeeze-Excitation Networks and Beyond

Abstract

The Non-Local Network (NLNet) presents a pioneering approach for capturing long-range dependencies, via aggregating query-specific global context to each query position. However, through a rigorous empirical analysis, we have found that the global contexts modeled by non-local network are almost the same for different query positions within an image. In this paper, we take advantage of this finding to create a simplified network based on a queryindependent formulation, which maintains the accuracy of NLNet but with significantly less computation. We further observe that this simplified design shares similar structure with Squeeze-Excitation Network (SENet). Hence we unify them into a three-step general framework for global context modeling. Within the general framework, we design a better instantiation, called the global context (GC) block, which is lightweight and can effectively model the global context. The lightweight property allows us to apply it for multiple layers in a backbone network to construct a global context network (GCNet), which generally outperforms both simplified NLNet and SENet on major benchmarks for various recognition tasks. The code and configurations are released at https://github.com/xvjiarui/GCNet.

UPI-Net: Semantic Contour Detection in Placental Ultrasound

“…Attention-based global context modelling has been successfully applied in various visual recognition applications such as semantic segmentation [43], panoptic segmentation [23], video classification [35], generative adversarial networks [44], and representation learning [4,17,17,22,29,37,11]. It is recently reported that the non-local pixel-wise attention can be simpli- fied as a more memory-efficient query-independent attention without sacrificing performance [35,4]. Following this work, UPI-Net models the global context of placental ultrasound images via lightweight non-local heads and semantic enhancement heads without introducing a large amount of network parameters or computational overhead.…”

“…Our proposed UPI-Net ( Fig. 4) aims to address these potential issues by adding two types of feature refinement blocks in a nested deep architecture: (i) global context (GC) blocks [4]; (ii) convolutional group-wise enhancement (CGE) blocks. A GC block modulates low-level features via simplified non-local operations and channel recalibration operations.…”

“…After a channel recalibration transform (via 1 × 1 convolutions, r = 16 [17]), the calibrated weight is aggregated back to the original input via a broadcasting addition. As reported in [4], a GC block is a lightweight alternative to the non-local block [35] in modelling global context of the input feature map. In UPI-Net, we attach GC blocks to conv-1, conv-2 and conv-3 to refine features from the earlier stages of the network.…”

“…A non-PAS case where UPI separates the placenta from the myometrium is shown in (c), somewhat contaminated by signal dropout. sampling and (dilated) convolution layers [14,15,40,41], which is reported to be computationally inefficient and difficult to optimize in general [35,4]. To address this issue, a self-attention mechanism, originally born in natural language processing studies [34], can be introduced to explicitly model element-wise correlation [44,35] and has achieved success in video classification, object detection and segmentation [16,43].…”

“…Moreover, we observe false negatives in some low-contrast regions. We expect to alleviate these errors by incorporating long-range contextual cues [35,4]. To this end, we argue that it would be beneficial for UPI detectors to model global context of each spatial position in order to suppress false predictions thus improve detection performance.…”