REVIEW 5 cited by
Cross-Layer Retrospective Retrieving via Layer Attention
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Cross-Layer Retrospective Retrieving via Layer Attention
read the original abstract
More and more evidence has shown that strengthening layer interactions can enhance the representation power of a deep neural network, while self-attention excels at learning interdependencies by retrieving query-activated information. Motivated by this, we devise a cross-layer attention mechanism, called multi-head recurrent layer attention (MRLA), that sends a query representation of the current layer to all previous layers to retrieve query-related information from different levels of receptive fields. A light-weighted version of MRLA is also proposed to reduce the quadratic computation cost. The proposed layer attention mechanism can enrich the representation power of many state-of-the-art vision networks, including CNNs and vision transformers. Its effectiveness has been extensively evaluated in image classification, object detection and instance segmentation tasks, where improvements can be consistently observed. For example, our MRLA can improve 1.6% Top-1 accuracy on ResNet-50, while only introducing 0.16M parameters and 0.07B FLOPs. Surprisingly, it can boost the performances by a large margin of 3-4% box AP and mask AP in dense prediction tasks. Our code is available at https://github.com/joyfang1106/MRLA.
Forward citations
Cited by 5 Pith papers
-
Transformers with Selective Access to Early Representations
SATFormer uses a learned context-dependent gate for selective access to early-layer value representations in Transformers, improving loss and accuracy over static residual baselines.
-
Transformers with Selective Access to Early Representations
SATFormer uses a context-dependent gate for selective reuse of early Transformer representations, improving validation loss and zero-shot accuracy especially on retrieval benchmarks.
-
KromHC: Manifold-Constrained Hyper-Connections with Kronecker-Product Residual Matrices
KromHC uses Kronecker products of small doubly stochastic matrices to make Hyper-Connection residual matrices exactly balanced with O(n^2C) parameters, and matches or beats prior variants on small LLM pretraining runs.
-
Attention Residuals
Attention Residuals replaces fixed residual summation with input-dependent softmax attention over preceding layers, and a blocked variant is shown to improve uniformity and downstream performance in a 48B-parameter mo...
-
Enhancing Oracle Bone Inscription Recognition via Multi-Scale Layer Attention
MSLA is a new attention mechanism that models multi-scale and cross-layer interactions to achieve more accurate OBI recognition than prior attention methods.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.