To the best of our knowledge, this is the first work to explicitly address feature similarity issue in multi-column design. Extensive experiments on four challenging benchmarks (ShanghaiTech, UCF_CC_50, UCF-QNRF, and Mall) demonstrate the effectiveness of the proposed innovations as well as the superior performance over the state-of-the-art. More remarkably, our method can be easily applied to other existing multi-column models as a plug-in to significantly boost the performance to a large extent.
zuofengyouliang
commented
1 year ago
I have set the batch size to 1, but the problem of “CUDA out of memory Tried to allocate 38.49 GiB " still occurs when training on UCF-QNRF dataset