D-VQA
D-VQA copied to clipboard
PyTorch implementation of "Debiased Visual Question Answering from Feature and Sample Perspectives" (NeurIPS 2021)
These files can't be downloaded from the official website. Do you have these files?
Hello, can anyone tell me how this dataset is handled
# Patching CVE-2007-4559 Hi, we are security researchers from the Advanced Research Center at [Trellix](https://www.trellix.com). We have began a campaign to patch a widespread bug named CVE-2007-4559. CVE-2007-4559 is a...
Hi, I wish to reproduce the LXMERT(LXMERT without D-VQA) numbers reported in the paper. It would be helpful if you could provide me with a way to do this using...
Hi, thank you for your work on this. I keep getting a download error when downloading the trainval_36.zip file. Is there another link I can use to download this? Thanks...
Do you freeze the LXRT model parameters when you train LXMERT + D-VQA for 10 epochs ?
您好,我将box的注释解开后,重新生成特征,然后将其绘制出来,但是明显感觉有偏差,不知道您是否可以提供一份绘图的代码。  下面是我的代码 def plot_rect(image, boxes): img = Image.fromarray(np.uint8(image)) draw = ImageDraw.Draw(img) for k in range(2): box = boxes[k,:] print(box) drawrect(draw, box, outline='green', width=3) img = np.asarray(img) return img def...
I reproduced the result on the 2080ti entirely following your code, but only got 59.89? Which parameters are set incorrectly?